mlsanityData to 7 Oct 2026

Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?

arXiv 2002.09919 ↗First posted 23 Feb 2020cs.CL cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

Multi-hop question answering (QA) requires a model to retrieve and integrate information from different parts of a long text to answer a question. Humans answer this kind of complex questions via a divide-and-conquer approach. In this paper, we investigate whether top-performing models for multi-hop questions understand the underlying sub-questions like humans. We adopt a neural decomposition model to generate sub-questions for a multi-hop complex question, followed by extracting the corresponding sub-answers. We show that multiple state-of-the-art multi-hop QA models fail to correctly answer a large portion of sub-questions, although their corresponding multi-hop questions are correctly answered. This indicates that these models manage to answer the multi-hop questions using some partial clues, instead of truly understanding the reasoning paths. We also propose a new model which significantly improves the performance on answering the sub-questions. Our work takes a step forward towards building a more explainable multi-hop QA system.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 6; 2024: 6; 2025: 3; 2026: 5.

29 papers.

Sort:

By area:

  1. 2022Prompting GPT-3 To Be Reliablecited by 258
  2. 2023Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformerscited by 59
  3. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  4. 2024MoreHopQA: More Than Multi-hop Reasoningcited by 37
  5. 2021Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answeringcited by 33
  6. 2024Cofca: A Step-Wise Counterfactual Multi-hop QA benchmarkcited by 26
  7. 2023STREET: A Multi-Task Structured Reasoning and Explanation Benchmarkcited by 13
  8. 2024GenDec: A robust generative Question-decomposition method for Multi-hop reasoningcited by 13
  9. 2024Revisiting the Superficial Alignment Hypothesiscited by 12
  10. 2022Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probescited by 9
  11. 2022Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answeringcited by 7
  12. 2025The Missing Parts: Augmenting Fact Verification with Half-Truth Detectioncited by 7
17 more
  1. 2023Multilingual Event Extraction from Historical Newspaper Advertscited by 5
  2. 2023HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervisioncited by 5
  3. 2022A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehensioncited by 4
  4. 2024Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Processcited by 4
  5. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 4
  6. 2021Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Predictioncited by 3
  7. 2022Prompt-based Conservation Learning for Multi-hop Question Answeringcited by 3
  8. 2023In-Context Ability Transfer for Question Decomposition in Complex QAcited by 3
  9. 2023Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answeringcited by 2
  10. 2022How Well Do Multi-hop Reading Comprehension Models Understand Date Information?cited by 1
  11. 2022Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Studycited by 1
  12. 2026Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detectioncited by 1
  13. 2025Multi-granular Training Strategies for Robust Multi-hop Reasoning Over Noisy and Heterogeneous Knowledge Sourcescited by 0
  14. 2026Evaluating Prompt Engineering Techniques for RAG in Small Language Models: A Multi-Hop QA Approachcited by 0
  15. 2026RespondeoQA: a Benchmark for Bilingual Latin-English Question Answeringcited by 0
  16. 2026Evaluating Hallucinations in Domain-Adapted Large Language Modelscited by 0
  17. 2026Locating Answer-Correctness Signals in Frozen Large Language Modelscited by 0